Harnessing Machine Learning and Image Processing for Prompt Disease Detection in Ocimum tenuiflorum Cultivation

The agricultural landscape of India, a cornerstone of its economy, faces significant challenges in the early detection of leaf diseases, particularly in the cultivation of Ocimumtenuiflorum, widely revered for its medicinal properties. This study innovatively employs advanced image-processing techniques combined with machine learning algorithms to enhance the accuracy and efficiency of identifying infections in Holy Basil plants. Utilizing a comprehensive dataset sourced from Plant Village, which includes various infected leaf types and healthy specimens, we implemented a robust framework for image augmentation, preprocessing, and feature extraction. Our evaluation of multiple machine learning classifiers reveals that the random forest algorithm achieves the highest accuracy of $\mathbf{99.86\%}$, effectively outperforming other models such as linear discriminant analysis and support vector machines. By merging traditional agricultural knowledge with modern computational tools, this research not only demonstrates a novel approach to disease management in Ocimumtenuiflorum but also underscores the potential for technology to transform agricultural practices, promoting sustainability and enhancing crop productivity in India.